%0 Conference Paper %1 NguyenNPB09 %A Nguyen, Dat Quoc %A Nguyen, Dai Quoc %A Pham, Son Bao %A Bui, The Duy %B Proceedings of the 2009 International Conference on Knowledge and Systems Engineering %D 2009 %I IEEE Computer Society %K information-retrieval myown template-based %P 232--236 %T A Fast Template-Based Approach to Automatically Identify Primary Text Content of a Web Page %U http://dx.doi.org/10.1109/KSE.2009.39 %X Search engines have become an indispensable tool for browsing information on the Internet. The user, however, is often annoyed by redundant results from irrelevant web pages. One reason is because search engines also look at noninformative blocks of web pages such as advertisement, navigation links, etc. In this paper, we propose a fast algorithm called FastContentExtractor to automatically detect main content blocks in a web page by improving the ContentExtractor algorithm. By automatically identifying and storing templates representing the structure of content blocks in a website, content blocks of a new web page from the website can be extracted quickly. The hierarchical order of the output blocks is also maintained which guarantees that the extracted content blocks are in the same order as the original ones.

@inproceedings{NguyenNPB09, abstract = {Search engines have become an indispensable tool for browsing information on the Internet. The user, however, is often annoyed by redundant results from irrelevant web pages. One reason is because search engines also look at noninformative blocks of web pages such as advertisement, navigation links, etc. In this paper, we propose a fast algorithm called FastContentExtractor to automatically detect main content blocks in a web page by improving the ContentExtractor algorithm. By automatically identifying and storing templates representing the structure of content blocks in a website, content blocks of a new web page from the website can be extracted quickly. The hierarchical order of the output blocks is also maintained which guarantees that the extracted content blocks are in the same order as the original ones.}, added-at = {2012-03-31T01:34:10.000+0200}, author = {Nguyen, Dat Quoc and Nguyen, Dai Quoc and Pham, Son Bao and Bui, The Duy}, biburl = {https://www.bibsonomy.org/bibtex/2b27ef73f062b24a388120889b2b35006/dqnguyen}, booktitle = {Proceedings of the 2009 International Conference on Knowledge and Systems Engineering}, interhash = {85e134ada3a9632f98458cd7dd90ca32}, intrahash = {b27ef73f062b24a388120889b2b35006}, keywords = {information-retrieval myown template-based}, pages = {232--236}, publisher = {IEEE Computer Society}, series = {KSE 2009}, timestamp = {2014-04-16T03:48:09.000+0200}, title = {A Fast Template-Based Approach to Automatically Identify Primary Text Content of a Web Page}, url = {http://dx.doi.org/10.1109/KSE.2009.39}, year = 2009 }